ML Anthology

Three-Dimensional Object Recognition Using an Unsupervised BCM Network: The Usefulness of Distinguishing Features

Nathan Intrator, Joshua I. Gold
NeCo 1993 pp. 61-74
doi:10.1162/NECO.1993.5.1.61 /neco/1993/intrator1993neco-threedimensional/

Abstract

We propose an object recognition scheme based on a method for feature extraction from gray level images that corresponds to recent statistical theory, called projection pursuit, and is derived from a biologically motivated feature extracting neuron. To evaluate the performance of this method we use a set of very detailed psychophysical three-dimensional object recognition experiments (Bülthoff and Edelman 1992).

PDF NeCo Semantic Scholar

Cite

Text

Intrator and Gold. "Three-Dimensional Object Recognition Using an Unsupervised BCM Network: The Usefulness of Distinguishing Features." Neural Computation, 1993. doi:10.1162/NECO.1993.5.1.61

Markdown

[Intrator and Gold. "Three-Dimensional Object Recognition Using an Unsupervised BCM Network: The Usefulness of Distinguishing Features." Neural Computation, 1993.](https://mlanthology.org/neco/1993/intrator1993neco-threedimensional/) doi:10.1162/NECO.1993.5.1.61

BibTeX

@article{intrator1993neco-threedimensional,
  title     = {{Three-Dimensional Object Recognition Using an Unsupervised BCM Network: The Usefulness of Distinguishing Features}},
  author    = {Intrator, Nathan and Gold, Joshua I.},
  journal   = {Neural Computation},
  year      = {1993},
  pages     = {61-74},
  doi       = {10.1162/NECO.1993.5.1.61},
  volume    = {5},
  url       = {https://mlanthology.org/neco/1993/intrator1993neco-threedimensional/}
}